Moonshot AI
Kimi K3.1 Pro
Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...
Cost / 1M tokens
High usage$2.00
input
$0.20
cached input
$10.00
output
Context Window
1M
Up to 944K max output
Architecture
1T+ MoE · 1M context
text + image + video → text
Quickstart & API
moonshotai/kimi-k3.1-proBest for & Strengths
Key Strengths
Recommended Workloads in ChatOSS
- Complex repository architecture
- Frontend & UI component design
- Long-horizon engineering
Verified Evaluations
Benchmarks & Frontier Comparison
How Kimi K3.1 Pro compares against leading open-weight and proprietary frontier models across independent agentic coding and reasoning suites.
| Benchmark (Metric) | Kimi K3.1 Pro | DeepSeek V4.1 Flash | GLM 5.3 | Claude Opus 5.5 | Gemini 4 Argon |
|---|---|---|---|---|---|
| Agentic & Software Engineering | |||||
| ChatOSS Agentic Coding Index (%) | 65% | 63.2% | 58.3% | 74.1% | 73.9% |
| SWE-Bench Verified (%) | 94.8% | 91.5% | 95.4% | 97% | 94% |
| DeepSWE v1.1 (Pass@1 %) | 73.5% | 77% | 69% | 74.2% | 77.9% |
| Vibe Code Bench v1.1 (%) | 88.4% | 87.7% | 78.1% | 90.3% | 91.9% |
| Terminal-Bench 4.0 (%) | 46.2% | 42.3% | 42% | 65.2% | 57.6% |
| Code Migration (%) | 52% | 45.6% | 44.2% | 66.7% | 68.2% |
| Intelligence & Token Economics | |||||
| Artificial Analysis Intelligence Index (0–100) | 55.1 | 39.5 | 44.8 | 57.6 | 52.6 |
| Input Price (/ 1M tokens) | $2.00 | $0.15 | $1.40 | $4.00 | $4.00 |
| Output Price (/ 1M tokens) | $10.00 | $0.60 | $4.40 | $20.00 | $20.00 |
ChatOSS Agentic Coding Index
ChatOSS Benchmark Audit · 4-benchmark composite mean
SWE-Bench Verified
Vals AI · Terminus 2
DeepSWE v1.1
DeepSWE / Official Audit · Mini-SWE-Agent
Vibe Code Bench v1.1
Vals.ai · OpenHands
Terminal-Bench 4.0
Vals.ai / Artificial Analysis · Terminus 2
Terminal-Bench 2.1
Vals.ai · Terminus 2
Code Migration
Vals.ai · Vals evaluation harness
Artificial Analysis Intelligence Index
Artificial Analysis
GPQA Diamond (Pass@1)
Benchmark Audit
Design Arena: 3D
Design Arena · Rank #2 (72.5% win)
Design Arena: Code Generation
Design Arena · Rank #6 (60.9% win)
Design Arena: Data Visualization
Design Arena · Rank #12 (56.7% win)
Design Arena: Game Dev
Design Arena · Rank #3 (66.7% win)
Active Provider Endpoints (2)
Upstream inference providers serving Kimi K3.1 Pro, with per-provider pricing, context limits, quantization, and 24-hour uptime.
| Provider | Input / 1M | Output / 1M | Cache Read / 1M | Context | Max Output | Quantization | Uptime (24h) |
|---|---|---|---|---|---|---|---|
Moonshot AIcache moonshotai/mxfp4 | $2.00 | $10.00 | $0.20 | 1M | 944K | mxfp4 | 100.0% |
Moonshot AIcache moonshotai/highspeed | $4.00 | $20.00 | $0.20 | 1M | 944K | mxfp4 | 100.0% |
Supported API Parameters
Parameters accepted by this model when called through ChatOSS or OpenRouter.
Deep-Dive Benchmarks & Teardowns
Independent benchmark analysis and real-world agent billing teardowns featuring Kimi K3.1 Pro.
Compare Similar Models
Browse all models →Moonshot AI
Kimi K3
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
Moonshot AI
Kimi K2.7 Code
MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...
Moonshot AI
Kimi K2.6
Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...
Moonshot AI
Kimi K2.5
Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...
Anthropic
Claude Opus 5.5
Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...
Anthropic
Claude Opus 5
Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...